Reinforcement-Learning-Driven Integrated Detection and Mitigation of UAV GPS Spoofing Attacks
Top Cited Papers
- 12 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (18) , 36926-36941
Abstract
Uncrewed aerial vehicles (UAVs) have demonstrated significant capabilities across various applications, including logistics, urban air mobility, surveillance, and defense. However, UAV operational effectiveness heavily depends on the global positioning system (GPS), which provides real-time navigation essential for mission success. UAV reliance on GPS introduces potential vulnerabilities to spoofing attacks, where adversaries transmit fictitious signals to disrupt navigation. This study proposes reinforcement learning-driven integrated detection and mitigation of UAV GPS spoofing attacks (RLDM-UAV), a novel reinforcement learning (RL) framework integrating detection and mitigation to ensure resilient UAV navigation. RLDM-UAV relies on GPS data and onboard camera inputs, eliminating the need for additional sensors. RLDM-UAV utilizes a deep Q-network (DQN)-based algorithm to enable dynamic GPS spoofing detection and adaptive switching between GPS-based and vision-based navigation policies based on the reliability of GPS signals. To enhance learning efficiency, we propose a novel experience replay mechanism that prioritizes incorrect detections. The average online computation time for the real-time detection and mitigation decision per time step is less than 23 ms on ARM-based CPUs. The performance of RLDM-UAV is evaluated against three types of GPS spoofing attacks: random attacks, replay attacks, and stealth attacks. The results demonstrate that RLDM-UAV achieves superior attack detection accuracies across all three types of GPS spoofing attacks and greater robustness under varying attack rates during testing compared to baseline methods.Keywords
Funding Information
- Department of Navy, Office of Naval Research (N00014-23-1-2626)
This publication has 47 references indexed in Scilit:
- Reinforcement learning with predefined and inferred reward machines in stochastic gamesNeurocomputing, 2024
- Decentralized graph-based multi-agent reinforcement learning using reward machinesNeurocomputing, 2023
- Knowledge-enhanced reinforcement learning for multi-machine integrated production and maintenance schedulingComputers & Industrial Engineering, 2023
- Bayesian Spatio-Temporal grAph tRansformer network (B-STAR) for multi-aircraft trajectory predictionKnowledge-Based Systems, 2022
- Optimal maintenance scheduling under uncertainties using Linear Programming-enhanced Reinforcement LearningEngineering Applications of Artificial Intelligence, 2022
- Secure trajectory planning against undetectable spoofing attacksAutomatica, 2020
- Unmanned Aircraft Capture and Control Via GPS SpoofingJournal of Field Robotics, 2014
- GPS‐denied Indoor and Outdoor Monocular Vision Aided Navigation and Control of Unmanned AircraftJournal of Field Robotics, 2013
- Practical Cryptographic Civil GPS Signal AuthenticationNAVIGATION: Journal of the Institute of Navigation, 2012
- RANGE–Robust autonomous navigation in GPS‐denied environmentsJournal of Field Robotics, 2011